@inproceedings{costa-jussa-etal-2025-2m,
    title = "2{M}-{BELEBELE}: Highly Multilingual Speech and {A}merican {S}ign {L}anguage Comprehension Dataset Download {PDF}",
    author = "Costa-juss{\`a}, Marta R.  and
      Yu, Bokai  and
      Andrews, Pierre  and
      Alastruey, Belen  and
      Camgoz, Necati Cihan  and
      Chuang, Joe  and
      Maillard, Jean  and
      Ropers, Christophe  and
      Turkatenko, Arina  and
      Wood, Carleigh",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.findings-acl.569/",
    pages = "10893--10904",
    ISBN = "979-8-89176-256-5",
    abstract = "We introduce the first highly multilingual speech and American Sign Language (ASL) comprehension dataset by extending BELEBELE. Our dataset covers 91 spoken languages at the intersection of BELEBELE and FLEURS, and one sign language (ASL). As a by-product we also extend the Automatic Speech Recognition Benchmark, FLEURS, by 20{\%}. We evaluate 2M-BELEBELE dataset for both 5-shot and zero-shot settings and across languages, the speech comprehension accuracy is {\ensuremath{\approx}} 10{\%} average lower compared to reading comprehension."
}